© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 49565
    Prev
    Next
    INDEX
    Explanations

    stylesheet href='../../../apidoc/stylesheets/bundled/bootstrap.min.css'/>text/javascript" charset="utf-8" src="./js/jquery.jscharset="utf-8

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asal
    -0.07
    uns
    -0.07
    <|box_end|>
    -0.07
    jaman
    -0.07
    å½ĵ代
    -0.07
    çĻ½å¤ľ
    -0.06
    arla
    -0.06
    åľ°ä¸İ
    -0.06
    à¸ļà¸Ńà¸Ļ
    -0.06
    rial
    -0.06
    POSITIVE LOGITS
    ERV
    0.07
    ÑģÑĤон
    0.06
     ansch
    0.06
    à¹Ģà¸Ĭà¹Īà¸Ļà¸ģัà¸Ļ
    0.06
    eby
    0.06
    ERGY
    0.06
    izont
    0.06
    ëij¥
    0.06
    anden
    0.06
     deÄŁiÅŁik
    0.06
    Activations Density 0.067%

    No Known Activations